Alibaba's Qwen Open-Sources Qwen3.8-2.4T-A95B Model
xiaosun86 · x · 2026-08-13
Alibaba's Qwen team has open-sourced the new Qwen3.8-2.4T-A95B model. The SGLang team shared empirical results showing the model's strong capability in handling complex engineering tasks; it autonomously ran for 4.5 hours to optimize its own SGLang serving with verified performance improvements. RadixArk's comparison tests indicated the model achieves 128 tok/s per user on SGLang.
More from Infra
- MLCommons launches MLPerf Endpoints, a benchmark that measures inference endpoints the way buyers actually purchase them — TheKanter · 2026-10-16
- AI-Driven Timing-Aware Power Optimization Uses Learned Ranking With Baseline-Preserving Repair — Amit Sharma · 2026-10-16
- Nscale AI datacenter plagued by coolant leaks, transformer fire, 10 safety violations — saranormous · 2026-10-16
- WSL 3.0 ships with native containers and Linux 6.18 kernel, syscall overhead down ~16% — solyarisoftware · 2026-10-16
- Are 22 GB modded RTX 2080 Ti cards a viable budget local LLM option? — Dave86ch · 2026-10-16
- Intel's neural-compressor: SOTA low-bit LLM quantization with FP4/NVFP4 support — HaihaoShen · 2026-10-16